Face Generation¶

In this project, you'll use generative adversarial networks to generate new images of faces.

Get the Data¶

You'll be using two datasets in this project:

MNIST
CelebA

Since the celebA dataset is complex and you're doing GANs in a project for the first time, we want you to test your neural network on MNIST before CelebA. Running the GANs on MNIST will allow you to see how well your model trains sooner.

If you're using FloydHub, set data_dir to "/input" and use the FloydHub data ID "R5KrjnANiKVhLWAkpXhNBe".

data_dir = './data'

# FloydHub - Use with data ID "R5KrjnANiKVhLWAkpXhNBe"
#data_dir = '/input'


"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import helper

helper.download_extract('mnist', data_dir)
helper.download_extract('celeba', data_dir)

Found mnist Data
Found celeba Data

Explore the Data¶

MNIST¶

As you're aware, the MNIST dataset contains images of handwritten digits. You can view the first number of examples by changing show_n_images.

show_n_images = 25

"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
%matplotlib inline
import os
from glob import glob
from matplotlib import pyplot

mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'mnist/*.jpg'))[:show_n_images], 28, 28, 'L')
pyplot.imshow(helper.images_square_grid(mnist_images, 'L'), cmap='gray')

<matplotlib.image.AxesImage at 0x7ff095ab9390>

CelebA¶

The CelebFaces Attributes Dataset (CelebA) dataset contains over 200,000 celebrity images with annotations. Since you're going to be generating faces, you won't need the annotations. You can view the first number of examples by changing show_n_images.

show_n_images = 25

"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'img_align_celeba/*.jpg'))[:show_n_images], 28, 28, 'RGB')
pyplot.imshow(helper.images_square_grid(mnist_images, 'RGB'))

<matplotlib.image.AxesImage at 0x7ff0959e1f60>

Preprocess the Data¶

Since the project's main focus is on building the GANs, we'll preprocess the data for you. The values of the MNIST and CelebA dataset will be in the range of -0.5 to 0.5 of 28x28 dimensional images. The CelebA images will be cropped to remove parts of the image that don't include a face, then resized down to 28x28.

The MNIST images are black and white images with a single color channel while the CelebA images have 3 color channels (RGB color channel).

Build the Neural Network¶

You'll build the components necessary to build a GANs by implementing the following functions below:

model_inputs
discriminator
generator
model_loss
model_opt
train

Check the Version of TensorFlow and Access to GPU¶

This will check to make sure you have the correct version of TensorFlow and access to a GPU

"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
from distutils.version import LooseVersion
import warnings
import tensorflow as tf

# Check TensorFlow Version
assert LooseVersion(tf.__version__) >= LooseVersion('1.0'), 'Please use TensorFlow version 1.0 or newer.  You are using {}'.format(tf.__version__)
print('TensorFlow Version: {}'.format(tf.__version__))

# Check for a GPU
if not tf.test.gpu_device_name():
    warnings.warn('No GPU found. Please use a GPU to train your neural network.')
else:
    print('Default GPU Device: {}'.format(tf.test.gpu_device_name()))

TensorFlow Version: 1.0.0
Default GPU Device: /gpu:0

Input¶

Implement the model_inputs function to create TF Placeholders for the Neural Network. It should create the following placeholders:

Real input images placeholder with rank 4 using image_width, image_height, and image_channels.
Z input placeholder with rank 2 using z_dim.
Learning rate placeholder with rank 0.

Return the placeholders in the following the tuple (tensor of real input images, tensor of z data)

import problem_unittests as tests

def model_inputs(image_width, image_height, image_channels, z_dim):
    """
    Create the model inputs
    :param image_width: The input image width
    :param image_height: The input image height
    :param image_channels: The number of image channels
    :param z_dim: The dimension of Z
    :return: Tuple of (tensor of real input images, tensor of z data, learning rate)
    """
    # TODO: Implement Function

    input_real = tf.placeholder(tf.float32, (None, image_width, image_height, image_channels) , name = 'input_real')
    input_z = tf.placeholder(tf.float32, (None, z_dim), name = 'input_z')
    learning_rate = tf.placeholder(tf.float32, [], name = 'learning_rate')
    
    
    return input_real, input_z, learning_rate


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_inputs(model_inputs)

Tests Passed

Leaky ReLU¶

def leaky_relu(x, alpha=0.05, name='leaky_relu'): 
    return tf.maximum(alpha * x, x, name=name)

Discriminator¶

Implement discriminator to create a discriminator neural network that discriminates on images. This function should be able to reuse the variabes in the neural network. Use tf.variable_scope with a scope name of "discriminator" to allow the variables to be reused. The function should return a tuple of (tensor output of the discriminator, tensor logits of the discriminator).

def discriminator(images, reuse=False, alpha = 0.2, rate = 0.1):
    """
    Create the discriminator network
    :param image: Tensor of input image(s)
    :param reuse: Boolean if the weights should be reused
    :return: Tuple of (tensor output of the discriminator, tensor logits of the discriminator)
    """
    # TODO: Implement Function

    with tf.variable_scope('discriminator', reuse = reuse):
        #input 28x28x3        
        images = tf.layers.conv2d(images, 128, 3, strides = 2, padding = 'same', kernel_initializer = tf.contrib.layers.xavier_initializer())                
        images = leaky_relu(images, alpha = alpha)
        images = tf.layers.dropout(images, rate, training= True)
        # 14x14x128
        
        images = tf.layers.conv2d(images, 256, 3, strides = 2, padding = 'same', use_bias=False, kernel_initializer = tf.contrib.layers.xavier_initializer())
        images = tf.layers.batch_normalization(images, training = True)
        images = leaky_relu(images, alpha = alpha)
        images = tf.layers.dropout(images, rate, training= True)
        #7x7x256
        
        images = tf.layers.conv2d(images, 512, 3, strides = 2, padding = 'same', use_bias=False, kernel_initializer = tf.contrib.layers.xavier_initializer())
        images = tf.layers.batch_normalization(images, training = True)
        images = leaky_relu(images, alpha = alpha)
        images = tf.layers.dropout(images, rate, training= True)
        #4x4x512
        
        #flatted
        flat = tf.reshape(images, (-1, 4 * 4 * 512))
        logits = tf.layers.dense(flat, 1, )
        out = tf.sigmoid(logits)
    
    return out, logits


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_discriminator(discriminator, tf)

Tests Passed

Generator¶

Implement generator to generate an image using z. This function should be able to reuse the variabes in the neural network. Use tf.variable_scope with a scope name of "generator" to allow the variables to be reused. The function should return the generated 28 x 28 x out_channel_dim images.

def generator(z, out_channel_dim, is_train=True, alpha=0.2, rate = 0.1):
    """
    Create the generator network
    :param z: Input z
    :param out_channel_dim: The number of channels in the output image
    :param is_train: Boolean if generator is being used for training
    :return: The tensor output of the generator
    """
    # TODO: Implement Function
    with tf.variable_scope('generator', reuse = not is_train):
        x = tf.layers.dense(z, 7 * 7 * 512,  use_bias=False, kernel_initializer = tf.contrib.layers.xavier_initializer())
        x = tf.reshape(x, (-1, 7, 7, 512))
        x = tf.layers.batch_normalization(x, training = is_train)
        x = leaky_relu(x, alpha = alpha)   
        x = tf.layers.dropout(x, rate, training= is_train)
        # 7x7x512
        
        x = tf.layers.conv2d_transpose(x, 256, 5, strides = 1, padding = 'same', use_bias=False, kernel_initializer = tf.contrib.layers.xavier_initializer())       
        x = tf.layers.batch_normalization(x, training = is_train)
        x = leaky_relu(x, alpha = alpha)
        x = tf.layers.dropout(x, rate, training= is_train)
        # 7x7x256
        
        x = tf.layers.conv2d_transpose(x, 128, 5, strides = 2, padding = 'same', use_bias=False, kernel_initializer = tf.contrib.layers.xavier_initializer())       
        x = tf.layers.batch_normalization(x, training = is_train)
        x = leaky_relu(x, alpha = alpha)
        x = tf.layers.dropout(x, rate, training= is_train)
        # 14x14x128
        
        logits = tf.layers.conv2d_transpose(x, out_channel_dim, 5, strides = 2, padding = 'same', kernel_initializer = tf.contrib.layers.xavier_initializer())
        # 28, 28, out_channel_dim
        
        out = tf.tanh(logits)
    
    
    return out


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_generator(generator, tf)

Tests Passed

Loss¶

Implement model_loss to build the GANs for training and calculate the loss. The function should return a tuple of (discriminator loss, generator loss). Use the following functions you implemented:

discriminator(images, reuse=False)
generator(z, out_channel_dim, is_train=True)

def model_loss(input_real, input_z, out_channel_dim, smooth = 0.1):
    """
    Get the loss for the discriminator and generator
    :param input_real: Images from the real dataset
    :param input_z: Z input
    :param out_channel_dim: The number of channels in the output image
    :return: A tuple of (discriminator loss, generator loss)
    """
    # TODO: Implement Function
    g_model = generator(input_z, out_channel_dim, is_train=True)
    d_model_real, d_logits_real = discriminator(input_real, reuse = False)
    d_model_fake, d_logits_fake = discriminator(g_model, reuse = True)
        

    d_loss_real = tf.reduce_mean(
        tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_real, labels=tf.random_uniform(tf.shape(d_model_real), 0.7, 1.2, tf.float32)))
    d_loss_fake = tf.reduce_mean(
        tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.random_uniform(tf.shape(d_logits_fake), 0, 0.3, tf.float32)))
    g_loss = tf.reduce_mean(
        tf.nn.sigmoid_cross_entropy_with_logits(logits=d_logits_fake, labels=tf.ones_like(d_model_fake)))


    d_loss = d_loss_real + d_loss_fake
    
    
    return d_loss, g_loss


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_loss(model_loss)

Tests Passed

Optimization¶

Implement model_opt to create the optimization operations for the GANs. Use tf.trainable_variables to get all the trainable variables. Filter the variables with names that are in the discriminator and generator scope names. The function should return a tuple of (discriminator training operation, generator training operation).

def model_opt(d_loss, g_loss, learning_rate, beta1):
    """
    Get optimization operations
    :param d_loss: Discriminator loss Tensor
    :param g_loss: Generator loss Tensor
    :param learning_rate: Learning Rate Placeholder
    :param beta1: The exponential decay rate for the 1st moment in the optimizer
    :return: A tuple of (discriminator training operation, generator training operation)
    """
    # TODO: Implement Function
    t_vars = tf.trainable_variables()
    d_vars = [var for var in t_vars if var.name.startswith('discriminator')]
    g_vars = [var for var in t_vars if var.name.startswith('generator')]
    
    # Optimize
    with tf.control_dependencies(tf.get_collection(tf.GraphKeys.UPDATE_OPS)):
        d_train_opt = tf.train.AdamOptimizer(learning_rate, beta1=beta1).minimize(d_loss, var_list=d_vars)
        g_train_opt = tf.train.AdamOptimizer(learning_rate, beta1=beta1).minimize(g_loss, var_list=g_vars)

    return d_train_opt, g_train_opt


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_model_opt(model_opt, tf)

Tests Passed

Neural Network Training¶

Show Output¶

Use this function to show the current output of the generator during training. It will help you determine how well the GANs is training.

"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import numpy as np

def show_generator_output(sess, n_images, input_z, out_channel_dim, image_mode):
    """
    Show example output for the generator
    :param sess: TensorFlow session
    :param n_images: Number of Images to display
    :param input_z: Input Z Tensor
    :param out_channel_dim: The number of channels in the output image
    :param image_mode: The mode to use for images ("RGB" or "L")
    """
    cmap = None if image_mode == 'RGB' else 'gray'
    z_dim = input_z.get_shape().as_list()[-1]
    example_z = np.random.uniform(-1, 1, size=[n_images, z_dim])

    samples = sess.run(
        generator(input_z, out_channel_dim, False),
        feed_dict={input_z: example_z})

    images_grid = helper.images_square_grid(samples, image_mode)
    pyplot.imshow(images_grid, cmap=cmap)
    pyplot.show()

Train¶

Implement train to build and train the GANs. Use the following functions you implemented:

model_inputs(image_width, image_height, image_channels, z_dim)
model_loss(input_real, input_z, out_channel_dim)
model_opt(d_loss, g_loss, learning_rate, beta1)

Use the show_generator_output to show generator output while you train. Running show_generator_output for every batch will drastically increase training time and increase the size of the notebook. It's recommended to print the generator output every 100 batches.

def train(epoch_count, batch_size, z_dim, learning_rate, beta1, get_batches, data_shape, data_image_mode, 
          print_every=10, show_every=50):
    """
    Train the GAN
    :param epoch_count: Number of epochs
    :param batch_size: Batch Size
    :param z_dim: Z dimension
    :param learning_rate: Learning Rate
    :param beta1: The exponential decay rate for the 1st moment in the optimizer
    :param get_batches: Function to get batches
    :param data_shape: Shape of the data
    :param data_image_mode: The image mode to use for images ("RGB" or "L")
    """
        
    # TODO: Build Model      
    
    input_real, input_z, lr = model_inputs(data_shape[1], data_shape[2], data_shape[3], z_dim)
    d_loss, g_loss = model_loss(input_real, input_z, data_shape[3])
    d_opt, g_opt = model_opt(d_loss, g_loss, lr, beta1)
    
    steps = 0
    
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        for epoch_i in range(epoch_count):            
            for batch_images in get_batches(batch_size):
                # TODO: Train Model                
                steps = steps + 1
                images = batch_images * 2
                
                # Sample random noise for G
                batch_z = np.random.uniform(-1, 1, size=(batch_size, z_dim))

                # Run optimizers
                _ = sess.run(d_opt, feed_dict={input_real: images, input_z: batch_z, lr: learning_rate})
                _ = sess.run(g_opt, feed_dict={input_real: images, input_z: batch_z, lr: learning_rate})
                                
                if steps % print_every == 0:
                   
                    train_loss_d = d_loss.eval({input_z: batch_z, input_real: images})
                    train_loss_g = g_loss.eval({input_z: batch_z})

                    print("Epoch {}/{}...".format(epoch_i + 1, epochs),
                          "Discriminator Loss: {:.4f}...".format(train_loss_d),
                          "Generator Loss: {:.4f}".format(train_loss_g))

                if steps % show_every == 0:                    
                    show_generator_output(sess, n_images = 16, 
                                          input_z = input_z, out_channel_dim = data_shape[3], image_mode = data_image_mode)

MNIST¶

Test your GANs architecture on MNIST. After 2 epochs, the GANs should be able to generate images that look like handwritten digits. Make sure the loss of the generator is lower than the loss of the discriminator or close to 0.

batch_size = 64
z_dim = 100
learning_rate = 0.0002
beta1 = 0.5
tf.reset_default_graph()

"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
epochs = 2

mnist_dataset = helper.Dataset('mnist', glob(os.path.join(data_dir, 'mnist/*.jpg')))
with tf.Graph().as_default():
    train(epochs, batch_size, z_dim, learning_rate, beta1, mnist_dataset.get_batches,
          mnist_dataset.shape, mnist_dataset.image_mode)

Epoch 1/2... Discriminator Loss: 0.9048... Generator Loss: 1.4293
Epoch 1/2... Discriminator Loss: 0.8907... Generator Loss: 1.4096
Epoch 1/2... Discriminator Loss: 0.9661... Generator Loss: 1.2903
Epoch 1/2... Discriminator Loss: 0.8737... Generator Loss: 2.2724
Epoch 1/2... Discriminator Loss: 1.3895... Generator Loss: 0.5449

Epoch 1/2... Discriminator Loss: 1.3545... Generator Loss: 0.7373
Epoch 1/2... Discriminator Loss: 1.3025... Generator Loss: 1.0606
Epoch 1/2... Discriminator Loss: 1.2244... Generator Loss: 1.2276
Epoch 1/2... Discriminator Loss: 1.1810... Generator Loss: 0.7516
Epoch 1/2... Discriminator Loss: 1.0227... Generator Loss: 0.9137

Epoch 1/2... Discriminator Loss: 1.0823... Generator Loss: 0.7456
Epoch 1/2... Discriminator Loss: 1.4213... Generator Loss: 0.5380
Epoch 1/2... Discriminator Loss: 1.3125... Generator Loss: 0.6887
Epoch 1/2... Discriminator Loss: 1.4333... Generator Loss: 0.5186
Epoch 1/2... Discriminator Loss: 1.3121... Generator Loss: 0.9300

Epoch 1/2... Discriminator Loss: 1.0665... Generator Loss: 1.1984
Epoch 1/2... Discriminator Loss: 1.1928... Generator Loss: 0.6386
Epoch 1/2... Discriminator Loss: 1.3488... Generator Loss: 0.5662
Epoch 1/2... Discriminator Loss: 1.1950... Generator Loss: 1.0890
Epoch 1/2... Discriminator Loss: 1.1108... Generator Loss: 0.8386

Epoch 1/2... Discriminator Loss: 1.1359... Generator Loss: 1.2843
Epoch 1/2... Discriminator Loss: 1.1298... Generator Loss: 0.6961
Epoch 1/2... Discriminator Loss: 1.1935... Generator Loss: 1.2538
Epoch 1/2... Discriminator Loss: 1.0792... Generator Loss: 1.0816
Epoch 1/2... Discriminator Loss: 1.3770... Generator Loss: 0.4272

Epoch 1/2... Discriminator Loss: 1.1493... Generator Loss: 0.7355
Epoch 1/2... Discriminator Loss: 1.2979... Generator Loss: 0.5513
Epoch 1/2... Discriminator Loss: 1.1884... Generator Loss: 0.8228
Epoch 1/2... Discriminator Loss: 1.0579... Generator Loss: 0.9115
Epoch 1/2... Discriminator Loss: 1.0622... Generator Loss: 0.8652

Epoch 1/2... Discriminator Loss: 1.1535... Generator Loss: 0.8364
Epoch 1/2... Discriminator Loss: 1.0133... Generator Loss: 1.0906
Epoch 1/2... Discriminator Loss: 1.1366... Generator Loss: 1.0899
Epoch 1/2... Discriminator Loss: 1.0708... Generator Loss: 0.8973
Epoch 1/2... Discriminator Loss: 1.0065... Generator Loss: 0.8837

Epoch 1/2... Discriminator Loss: 1.1428... Generator Loss: 0.7979
Epoch 1/2... Discriminator Loss: 1.1542... Generator Loss: 0.6537
Epoch 1/2... Discriminator Loss: 1.2623... Generator Loss: 1.6560
Epoch 1/2... Discriminator Loss: 1.1038... Generator Loss: 0.6788
Epoch 1/2... Discriminator Loss: 1.1159... Generator Loss: 0.6345

Epoch 1/2... Discriminator Loss: 1.0762... Generator Loss: 0.7516
Epoch 1/2... Discriminator Loss: 0.9569... Generator Loss: 0.9102
Epoch 1/2... Discriminator Loss: 1.2007... Generator Loss: 1.5063
Epoch 1/2... Discriminator Loss: 1.1720... Generator Loss: 0.7625
Epoch 1/2... Discriminator Loss: 1.2075... Generator Loss: 0.6122

Epoch 1/2... Discriminator Loss: 1.1548... Generator Loss: 1.5305
Epoch 1/2... Discriminator Loss: 1.0361... Generator Loss: 1.0775
Epoch 1/2... Discriminator Loss: 1.3118... Generator Loss: 0.4751
Epoch 1/2... Discriminator Loss: 1.1562... Generator Loss: 0.5281
Epoch 1/2... Discriminator Loss: 1.2852... Generator Loss: 0.5664

CelebA¶

Run your GANs on CelebA. It will take around 20 minutes on the average GPU to run one epoch. You can run the whole epoch or stop when it starts to generate realistic faces.

batch_size = 64
z_dim = 100
learning_rate = 0.0002
beta1 = 0.5
tf.reset_default_graph()

"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
epochs = 1

celeba_dataset = helper.Dataset('celeba', glob(os.path.join(data_dir, 'img_align_celeba/*.jpg')))
with tf.Graph().as_default():
    train(epochs, batch_size, z_dim, learning_rate, beta1, celeba_dataset.get_batches,
          celeba_dataset.shape, celeba_dataset.image_mode)

Epoch 1/1... Discriminator Loss: 1.0202... Generator Loss: 1.1558
Epoch 1/1... Discriminator Loss: 0.9778... Generator Loss: 0.7002
Epoch 1/1... Discriminator Loss: 1.0340... Generator Loss: 0.7037
Epoch 1/1... Discriminator Loss: 1.0042... Generator Loss: 1.5187
Epoch 1/1... Discriminator Loss: 2.3447... Generator Loss: 0.1739

Epoch 1/1... Discriminator Loss: 1.0384... Generator Loss: 2.4741
Epoch 1/1... Discriminator Loss: 2.1601... Generator Loss: 0.2214
Epoch 1/1... Discriminator Loss: 1.3886... Generator Loss: 0.6768
Epoch 1/1... Discriminator Loss: 1.0982... Generator Loss: 0.9572
Epoch 1/1... Discriminator Loss: 1.0481... Generator Loss: 0.9522

Epoch 1/1... Discriminator Loss: 0.9742... Generator Loss: 0.9582
Epoch 1/1... Discriminator Loss: 1.1661... Generator Loss: 1.0590
Epoch 1/1... Discriminator Loss: 0.9651... Generator Loss: 1.1782
Epoch 1/1... Discriminator Loss: 1.1658... Generator Loss: 1.5918
Epoch 1/1... Discriminator Loss: 1.0974... Generator Loss: 0.6662

Epoch 1/1... Discriminator Loss: 1.3159... Generator Loss: 0.8248
Epoch 1/1... Discriminator Loss: 1.1138... Generator Loss: 0.6628
Epoch 1/1... Discriminator Loss: 1.0206... Generator Loss: 1.6743
Epoch 1/1... Discriminator Loss: 0.9505... Generator Loss: 1.6200
Epoch 1/1... Discriminator Loss: 1.1375... Generator Loss: 0.6896

Epoch 1/1... Discriminator Loss: 1.0471... Generator Loss: 0.7615
Epoch 1/1... Discriminator Loss: 1.1330... Generator Loss: 0.7355
Epoch 1/1... Discriminator Loss: 0.9984... Generator Loss: 1.7252
Epoch 1/1... Discriminator Loss: 1.5291... Generator Loss: 0.4287
Epoch 1/1... Discriminator Loss: 1.1349... Generator Loss: 1.6962

Epoch 1/1... Discriminator Loss: 1.0989... Generator Loss: 1.1991
Epoch 1/1... Discriminator Loss: 1.1296... Generator Loss: 0.6419
Epoch 1/1... Discriminator Loss: 1.0002... Generator Loss: 0.9738
Epoch 1/1... Discriminator Loss: 0.9866... Generator Loss: 1.2523
Epoch 1/1... Discriminator Loss: 0.9979... Generator Loss: 2.4154

Epoch 1/1... Discriminator Loss: 0.9074... Generator Loss: 1.6089
Epoch 1/1... Discriminator Loss: 1.1471... Generator Loss: 1.5552
Epoch 1/1... Discriminator Loss: 1.0004... Generator Loss: 0.7134
Epoch 1/1... Discriminator Loss: 1.2664... Generator Loss: 2.8606
Epoch 1/1... Discriminator Loss: 0.9393... Generator Loss: 1.1904

Epoch 1/1... Discriminator Loss: 0.9843... Generator Loss: 1.5069
Epoch 1/1... Discriminator Loss: 1.1106... Generator Loss: 0.6704
Epoch 1/1... Discriminator Loss: 1.0025... Generator Loss: 0.7382
Epoch 1/1... Discriminator Loss: 1.0001... Generator Loss: 1.9771
Epoch 1/1... Discriminator Loss: 1.0213... Generator Loss: 1.2184

Epoch 1/1... Discriminator Loss: 1.0556... Generator Loss: 1.4921
Epoch 1/1... Discriminator Loss: 1.1716... Generator Loss: 1.3657
Epoch 1/1... Discriminator Loss: 1.0399... Generator Loss: 1.3537
Epoch 1/1... Discriminator Loss: 1.0079... Generator Loss: 1.1416
Epoch 1/1... Discriminator Loss: 0.9599... Generator Loss: 1.0134

Epoch 1/1... Discriminator Loss: 1.3299... Generator Loss: 0.5279
Epoch 1/1... Discriminator Loss: 1.3647... Generator Loss: 0.5338
Epoch 1/1... Discriminator Loss: 0.9951... Generator Loss: 0.9584
Epoch 1/1... Discriminator Loss: 0.9430... Generator Loss: 1.2518
Epoch 1/1... Discriminator Loss: 1.0474... Generator Loss: 1.5125

Submitting This Project¶

When submitting this project, make sure to run all the cells before saving the notebook. Save the notebook file as "dlnd_face_generation.ipynb" and save it as a HTML file under "File" -> "Download as". Include the "helper.py" and "problem_unittests.py" files in your submission.